© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 39327
    Prev
    Next
    INDEX
    Explanations

    any or everything

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¾Īå¤ļæŶåĢĻ
    -0.09
    ichel
    -0.09
    uper
    -0.09
    å¥Ĺè·¯
    -0.09
    å¾Īå¤ļäºĭæĥħ
    -0.08
    è¯Ŀ说
    -0.08
     Madden
    -0.08
    忧èĻij
    -0.08
    ardin
    -0.08
    athe
    -0.08
    POSITIVE LOGITS
    碰
    0.11
    åı¯çĶ¨
    0.11
    碰åĪ°
    0.10
    åĩ¡
    0.10
    åıªè¦ģæĺ¯
    0.10
    æīĢèĥ½
    0.09
    éĢ®
    0.09
    æݥ触åĪ°
    0.09
     available
    0.09
    对æīĭ
    0.09
    Activations Density 0.085%

    No Known Activations